Node Embeddings for Graph Merging: Case of Knowledge Graph Construction
Node Embeddings for Graph Merging: Case of Knowledge Graph Construction
复制标题
DOI：
10.18653/v1/d19-5321
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Ida Szubert;Mark Steedman
中科院分区：
文献类型：
--
作者：
Ida Szubert;Mark Steedman
合并两个图需要合并彼此对应的节点。在此过程中会发生错误，导致不正确的合并或不正确的合并失败。我们发现在使用AskNET（一种从文本语料库构建知识图的算法）时，这种错误的发生率很高。AskNET节点匹配方法使用字符串相似度，我们提出用向量嵌入相似度代替字符串相似度。我们探索了基于图和基于词的嵌入模型，并显示了总体误差从56%减少到23.6%，两种类型的错误节点匹配都减少了一半以上。
Combining two graphs requires merging the nodes which are counterparts of each other. In this process errors occur, resulting in incorrect merging or incorrect failure to merge. We find a high prevalence of such errors when using AskNET, an algorithm for building Knowledge Graphs from text corpora. AskNET node matching method uses string similarity, which we propose to replace with vector embedding similarity. We explore graph-based and word-based embedding models and show an overall error reduction of from 56% to 23.6%, with a reduction of over a half in both types of incorrect node matching.